This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA4VM: Can't output bin file after running onnxrt_ep.py

Part Number: TDA4VM

 Hi, I want to convert my onnx model to TIDL bin files using edge Ai tools, and this error occurs.

I'm using example models 

models = ['cl-ort-resnet18-v1', 'ss-ort-deeplabv3lite_mobilenetv2', 'od-ort-ssd-lite_mobilenetv2_fpn']

File "/media/tsingyueliu/1e871d72-bcd5-485f-99b4-e0a85ce8bf1d/edgeai-tidl-tools/examples/osrt_python/ort/onnxrt_ep.py", line 281, in <module>
    run_model(model, mIdx)
  File "/media/tsingyueliu/1e871d72-bcd5-485f-99b4-e0a85ce8bf1d/edgeai-tidl-tools/examples/osrt_python/ort/onnxrt_ep.py", line 201, in run_model
    imgs, output, proc_time, sub_graph_time, height, width  = infer_image(sess, input_images, config)
  File "/media/tsingyueliu/1e871d72-bcd5-485f-99b4-e0a85ce8bf1d/edgeai-tidl-tools/examples/osrt_python/ort/onnxrt_ep.py", line 121, in infer_image
    copy_time, sub_graphs_proc_time, totaltime = get_benchmark_output(sess)
  File "/media/tsingyueliu/1e871d72-bcd5-485f-99b4-e0a85ce8bf1d/edgeai-tidl-tools/examples/osrt_python/ort/onnxrt_ep.py", line 70, in get_benchmark_output
    benchmark_dict = interpreter.get_TI_benchmark_data()
AttributeError: 'InferenceSession' object has no attribute 'get_TI_benchmark_data'

# copy_time, sub_graphs_proc_time, totaltime = get_benchmark_output(sess)
# proc_time = totaltime - copy_time

After I commented two lines included get_benchmark_output, it works, but I couldn't find any bin files.

How can I get bin files that can be deployed onto TDA4?

Thanks!